Autonomous real-time surveillance system with distributed IP cameras

Abstract

Abstract-An autonomous Internet Protocol (IP) camera based object tracking and behaviour identification system, capable of running in real-time on an embedded system with limited memory and processing power is presented in this paper. The main contribution of this work is the integration of processor intensive image processing algorithms on an embedded platform capable of running at real-time for monitoring the behaviour of pedestrians. The Algorithm Based Object Recognition and Tracking (ABORAT) system architecture presented here was developed on an Intel PXA270-based development board clocked at 520 MHz. The platform was connected to a commercial stationary IP-based camera in a remote monitoring station for intelligent image processing. The system is capable of detecting moving objects and their shadows in a complex environment with varying lighting intensity and moving foliage. Objects moving close to each other are also detected to extract their trajectories which are then fed into an unsupervised neural network for autonomous classification. The novel intelligent video system presented is also capable of performing simple analytic functions such as tracking and generating alerts when objects enter/leave regions or cross tripwires superimposed on live video by the operator.

Distributed human detection on mobile platform

“…Object identification allows the system to identify objects present in the video or images captured [10]. This may include but are not limited to humans, faces or vehicles.…”

“…Development have been done in the field of automatic and intelligent surveillance systems [10] with the goal of reducing the occurrence of human error. These systems are able to automatically detect and react to predefined events such as movement or the presence of specific objects in the scene.…”

Adaptive background modeling in multicamera system for real-time object detection

“…28 Recently, a great attention has been paid to MoG algorithms based on Compute Unified Device Architecture (CUDA). 29,30 These types of solutions are very efficient, but they cannot be easily adapted to consumer applications, where conventional cameras are used and specific and expensive hardware is avoided.…”

Binary histogram based split/merge object detection using FPGAs

“…Visual surveillance systems usually have the ability to detect moving objects, track them in the field of view and perform high level behavioural analysis [1]. When the camera is stationary, a natural approach to detect moving objects is to use background differencing, in which a reference image is maintained and constantly updated to reflect changes in the scene.…”